Question

我正在使用各种c（“s_size”，“reps”）的c（“x”，“y”，“density”）列对数据帧中的行进行二次取样。 Reps = replicates，s_size =从整个数据帧中子采样的行数。

> head(data_xyz)
   x y density
1  6 1       0
2  7 1   17600
3  8 1   11200
4 12 1   14400
5 13 1       0
6 14 1    8000



 #Subsampling###################
    subsample_loop <- function(s_size, reps, int) {
      tm1 <- system.time( #start timer
    {
      subsample_bound = data.frame()
    #Perform Subsampling of the general 
    for (s_size in seq(1,s_size,int)){
      for (reps in 1:reps) {
        subsample <- sample.df.rows(s_size, data_xyz)
         assign(paste("sample" ,"_","n", s_size, "_", "r", reps , sep=""), subsample)
        subsample_replicate <- subsample[,] #temporary variable
        subsample_replicate <- cbind(subsample, rep(s_size,(length(subsample_replicate[,1]))),
                                     rep(reps,(length(subsample_replicate[,1]))))
        subsample_bound <- rbind(subsample_bound, subsample_replicate)

      }
    }
    }) #end timer
      colnames(subsample_bound) <- c("x","y","density","s_size","reps")
    subsample_bound
    } #end function

Here's the function call:

    source("R/functions.R")
    subsample_data <- subsample_loop(s_size=206, reps=5, int=10)

这是行子样本函数：

# Samples a number of rows in a dataframe, outputs a dataframe of the same # of columns
# df Data Frame
# N number of samples to be taken
sample.df.rows <- function (N, df, ...) 
  { 
    df[sample(nrow(df), N, replace=FALSE,...), ] 
  }

这太慢了，我已经尝试了几次应用函数并没有运气。我将从1：250为每个s_size做大约1,000-10,000次重复。

让我知道你的想法！提前谢谢。

=============================================== ========================== 更新编辑：从中抽样的样本数据： https://www.dropbox.com/s/47mpo36xh7lck0t/density.csv

Joran在函数中的代码（在sourced function.R文件中）：

foo <- function(i,j,data){
  res <- data[sample(nrow(data),i,replace = FALSE),]
  res$s_size <- i
  res$reps <- rep(j,i)
  res
}
resampling_custom <- function(dat, s_size, int, reps) {
  ss <- rep(seq(1,s_size,by = int),each = reps)
  id <- rep(seq_len(reps),times = s_size/int)
  out <- do.call(rbind,mapply(foo,i = ss,j = id,MoreArgs = list(data = dat),SIMPLIFY = FALSE))
}

调用函数

set.seed(2)
out <- resampling_custom(dat=retinal_xyz, s_size=206, int=5, reps=10)

不幸的是，

输出数据警告消息：

Warning message:
In mapply(foo, i = ss, j = id, MoreArgs = list(data = dat), SIMPLIFY = FALSE) :
  longer argument not a multiple of length of shorter

Answer 1

我很少考虑实际优化这一点，我只是专注于做一些至少合理的事情，同时匹配你的程序。

您最大的问题是您通过rbind和cbind种植对象。基本上，只要您看到有人写data.frame()或c()并使用rbind，cbind或c展开该对象，您就可以确定生成的代码将会实质上是尝试任务的最慢的方式。

这个版本的速度提高了大约12-13倍，如果你真的想到它，我相信你可以从中榨取更多的东西：

s_size <- 200
int <- 10
reps <- 30

ss <- rep(seq(1,s_size,by = int),each = reps)
id <- rep(seq_len(reps),times = s_size/int)

foo <- function(i,j,data){
    res <- data[sample(nrow(data),i,replace = FALSE),]
    res$s_size <- i
    res$reps <- rep(j,i)
    res
}

out <- do.call(rbind,mapply(foo,i = ss,j = id,MoreArgs = list(data = dat),SIMPLIFY = FALSE))

关于R的最好的部分是，不仅这种方式更快，而且代码也更少。

R：行重采样循环速度提高

1 个答案: